Skip to content

[RSS 2025] Learning to Act Anywhere with Task-centric Latent Actions

Python · active 2025-05-092026-07-09 (UTC)

Partial coverage13,594 / 16,231 hourly files (84%) · 2 absent upstream · 2,631 failed, retryable2024-10-042026-08-11 (UTC)— sampled evenly across the window, so rankings and trends hold; absolute counts scale up.
Events
711
Pushes
23
Pull requests
3
Issues
66
Stars
481
Forks
35

Activity over time

Daily event counts in the loaded window

Line chart, 427 days from 2025-05-09 to 2026-07-09. Pushes: 23 total, peak 3 in a day. Pull requests: 3 total, peak 2 in a day. Issues: 66 total, peak 4 in a day. Comments: 103 total, peak 6 in a day. Stars: 481 total, peak 28 in a day.

  • Pushes
  • Pull requests
  • Issues
  • Comments
  • Stars

Stars, PRs, issues and forks are under-captured in the later part of this window. GH Archive progressively stopped capturing non-push events during 2026 — −95% or worse by the end of the window. Every series here except Pushes fades for that reason, so a decline above reflects the archive, not this repository. Pushes stay reliable throughout, so read them, and the contributor counts derived from them, as the real signal. Data health has the measurements.

Top contributors

Pushes, PRs, issues, reviews and comments — stars and forks excluded, so this is contribution rather than popularity

Recent activity

Latest issues, pull requests and releases

  • Issue#7525616812442026-01-09 02:52
    self.dino_encoder = torch.hub.load('facebookresearch/dinov2', 'dinov2_vitb14_reg')
  • Issue comment#7421Broccoli2026-01-06 14:01
    StageB finetune
  • Issue comment#56Hitjss2025-12-24 09:01
    Question about CALVIN finetuning
  • Issue#72xuxiaoxxxx2025-12-08 06:52
    The confusion of stage1 in pretraining
  • Issue comment#72retsuh-bqw2025-12-05 09:31
    The confusion of stage1 in pretraining
  • Issue#72xuxiaoxxxx2025-11-21 11:48
    The confusion of stage1 in pretraining
  • Pull request#71OptimistiCompound2025-11-21 06:49
  • Pull request#71OptimistiCompound2025-11-21 06:49
  • Issue comment#60retsuh-bqw2025-11-19 02:57
    Loss instability when resuming pretraining from converted HF weights
  • Issue comment#60Nemo-10242025-11-18 05:32
    Loss instability when resuming pretraining from converted HF weights
  • Issue comment#65retsuh-bqw2025-10-02 06:37
    About exploiting wrist view camera
  • Issue#60minghaoguo202025-09-23 10:43
    Loss instability when resuming pretraining from converted HF weights
  • Issue comment#59ginwind2025-09-11 08:49
    Question about the python version of evaluating LIBERO
  • Issue comment#16Freq-q2025-09-11 08:27
    Error when calling get_latent_action function (During Libero evaluation)
  • Issue comment#59Freq-q2025-09-10 06:36
    Question about the python version of evaluating LIBERO
  • Issue#63retsuh-bqw2025-09-08 11:10
    Question: Why is T hard-coded as 2 in rearrange operation when num_frames can be different?
  • Issue comment#63retsuh-bqw2025-09-05 08:43
    Question: Why is T hard-coded as 2 in rearrange operation when num_frames can be different?
  • Issue#63sigongzi2025-09-05 08:35
    Question: Why is T hard-coded as 2 in rearrange operation when num_frames can be different?
  • Issue comment#62retsuh-bqw2025-09-04 08:18
    train loss and latent_action_accuracy when deploy univla to real world
  • Issue comment#62BarneetWei2025-09-04 07:42
    train loss and latent_action_accuracy when deploy univla to real world
  • Issue#62BarneetWei2025-09-04 06:58
    train loss and latent_action_accuracy when deploy univla to real world
  • Issue comment#61feiyu121382025-09-02 04:22
    Training task-centric codebook (LAM stage-2)
  • Issue#61feiyu121382025-09-02 04:22
    Training task-centric codebook (LAM stage-2)
  • Issue comment#58retsuh-bqw2025-09-02 04:13
    training metric train/code_usage_step
  • Issue comment#61retsuh-bqw2025-09-02 03:39
    Training task-centric codebook (LAM stage-2)

Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 481 stars here means stars gained during the window, not the repo's star count.